adiamaan92

name: Modi Speech Scrapper
on:
  schedule:
    # Runs every day at 8 AM
    - cron: '0 8 * * *'
  # Run workflow manually (without waiting for the cron to be called), through the Github Actions Workflow page directly
  workflow_dispatch:

jobs:
  modi-speech-scrapper:

adiamaan92

{
	"title": "Narendra Modi - Text Speeches",
	"id": "adiamaan/modi-speeches",
	"subtitle": "Speeches of the Prime Minister of India",
	"description": "### Context\n**Narendra Damodaradas Modi** is an Indian politician serving as the 14th and current prime minister of India since 2014. Modi was the chief minister of Gujarat from 2001 to 2014 and is a Member of Parliament from Varanasi.\n\n![Modi](https://images.hindustantimes.com/img/2021/09/04/550x309/PTI09-03-2021-000085B-0_1630691680953_1630739078395.jpg)\n\nModi had a long political career, before quickly rising within his party from the Chief Minister of Gujarat (2001 - 2014) to the Primi Minister candidate in the 2014 election. Known for his excellent oratorical skills and ability to connect to the common man, **this dataset gives access to all his text speeches starting from 2018**.\n\n**This dataset will be updated every day**, adding in new speeches when it is available.\n\n### Content\nThe contents are scrapped from [Narendra Modi](https://www.narend

adiamaan92

updated_speeches = (
        pd.concat([delta_speeches, speeches])
    )
updated_speeches.to_csv("./data/modi_speeches.csv", index=False)
api.dataset_create_version(
    "./data/",
    version_notes=f"Updated on {datetime.datetime.now().strftime('%Y-%m-%d')}",
)

adiamaan92

from kaggle.api.kaggle_api_extended import KaggleApi

def get_speeches(api: KaggleApi) -> str:
    """Get latest speech from kaggle dataset
    Args:
        api (KaggleApi): Kaggle api
    Returns:
        Latest speech title from previous run
    """
    api.dataset_download_files("adiamaan/modi-speeches", path="./data", unzip=True)

adiamaan92

i = 1

while True:
    # This GET API request returns the ith page. The pages are sorted in descending order
    # based on the datetime it is published
    r = requests.get(
        f"https://www.narendramodi.in/speech/loadspeeche?page={i}&language=en",
        headers=headers,
    )
    

adiamaan92

import numpy as np


def generate_buddhabrot(non_mandelbrot: np.ndarray, size: int) -> np.ndarray:
    """Generate buddhabrot image array

    Args:
        non_manderlbrot (np.ndarray): Array of non-mandelbrot points on the complex plane
        size (int): Size of the image array

adiamaan92

import numpy as np


def make_non_mandelbrot_set(nsamples: int, max_iterations: int) -> np.ndarray:
    """Generate a set of complex numbers that are not in the Mandelbrot set.

    This employs some of the optimizations from this page,
    http://en.wikipedia.org/wiki/Mandelbrot_set#Optimizations

    In order to minimize run time, we are trying to reduce the number of points

adiamaan92

import numpy as np

x_dim, y_dim = 500, 500  
x = np.linspace(-2, 1, x_dim)
y = np.linspace(-1.5, 1.5, y_dim)

max_iterations = 100
array = np.zeroes((x_dim, y_dim))

for i in range(x):

adiamaan92

  {
  "editor.fontLigatures": true,
  "editor.fontFamily": "'Victor Mono','Fira Code', Consolas, 'Courier New', monospace",
  "editor.fontSize": 15,
  "editor.tokenColorCustomizations": {
    "textMateRules": [
      {
        "scope": [
          "invalid",
          "keyword.operator",

adiamaan92

def setcols(df, fn=lambda x: x.columns.map('_'.join), cols=None):
    """Sets the column of the data frame to the passed column list.
    """
    if cols:
        df.columns = cols
    else:
        df.columns = fn(df)
    return df